Model comparison
MiMo-V2.5 vs Nemotron 3 Ultra
MiMo-V2.5 and Nemotron 3 Ultra score almost the same on the Noometry Index (43.4 vs 42.5), so choose on price, context window or the category you care about most.
Last verified . 19 shared benchmarks.
NVIDIASummary
- They share 19 benchmarks with published results for both. MiMo-V2.5 scores higher in 4 categories and Nemotron 3 Ultra in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Nemotron 3 Ultra leads 52.5 to 40.8.
- The biggest single-benchmark swing is ProofBench: 16% for MiMo-V2.5 and 2% for Nemotron 3 Ultra.
- MiMo-V2.5 is cheaper at $0.14 / $0.28 per million input/output tokens, against $0.60 / $2.40 for Nemotron 3 Ultra.
- MiMo-V2.5 accepts more context: 1.05M tokens versus 262K.
Side by side
| MiMo-V2.5 | Nemotron 3 Ultra | |
|---|---|---|
| Provider | Xiaomi | NVIDIA |
| Noometry Index | 43.4 | 42.5 |
| Released | 2026-04-22 | 2026-06-04 |
| Weights | Open | Open |
| Context window | 1.05M | 262K |
| Max output | 131K | 128K |
| Input $ / M tokens | $0.14 | $0.60 |
| Output $ / M tokens | $0.28 | $2.40 |
| Results tracked | 23 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5 leads
MiMo-V2.5: 43.9 (#81), Nemotron 3 Ultra: 38.1 (#182)
| Benchmark | MiMo-V2.5 | Nemotron 3 Ultra |
|---|---|---|
| SciCode | 43.1% | 40.3% |
| LMArena Coding | 1469 | 1468 |
| FrontierCode | — | 13.6% |
| LMArena WebDev | 1438 | — |
| WeirdML | — | 43.5% |
| ALE-Bench | 513.95 | — |
Agentic & Tool Use Not comparable
MiMo-V2.5: —, Nemotron 3 Ultra: 23.4 (#126)
| Benchmark | MiMo-V2.5 | Nemotron 3 Ultra |
|---|---|---|
| APEX-Agents | — | 22.7% |
Reasoning Nemotron 3 Ultra leads
MiMo-V2.5: 28.6 (#101), Nemotron 3 Ultra: 31.0 (#82)
| Benchmark | MiMo-V2.5 | Nemotron 3 Ultra |
|---|---|---|
| CritPt | 3.7% | 3.1% |
| LMArena Hard Prompts | 1450 | 1452 |
| Chess Puzzles | — | 12% |
| Mystery Game Puzzles | — | 20% |
| DTBench | — | 90.1% |
| LMCA | — | 36.9% |
| Epoch Capabilities Index | — | 146.17 |
Math MiMo-V2.5 leads
MiMo-V2.5: 36.8 (#163), Nemotron 3 Ultra: 35.3 (#187)
| Benchmark | MiMo-V2.5 | Nemotron 3 Ultra |
|---|---|---|
| ProofBench | 16% | 2% |
| LMArena Math | 1436 | 1457 |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
Knowledge Nemotron 3 Ultra leads
MiMo-V2.5: 40.8 (#115), Nemotron 3 Ultra: 52.5 (#61)
| Benchmark | MiMo-V2.5 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Expert | 1460 | 1472 |
| GPQA Diamond | — | 85.4% |
Multimodal Not comparable
MiMo-V2.5: 39.8 (#54), Nemotron 3 Ultra: —
| Benchmark | MiMo-V2.5 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Vision | 1247 | — |
Multilingual Nemotron 3 Ultra leads
MiMo-V2.5: 51.9 (#99), Nemotron 3 Ultra: 53.5 (#64)
| Benchmark | MiMo-V2.5 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | 1404 | 1427 |
| LMArena Chinese | 1468 | 1497 |
| LMArena French | 1447 | 1472 |
| LMArena German | 1421 | 1471 |
| LMArena Korean | 1363 | 1386 |
| LMArena Russian | 1395 | 1417 |
| LMArena Spanish | 1416 | 1454 |
| LMArena Japanese | 1306 | — |
Instruction Following Too close to call
MiMo-V2.5: 75.5 (#60), Nemotron 3 Ultra: 74.7 (#88)
| Benchmark | MiMo-V2.5 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | 1434 | 1418 |
Long Context Too close to call
MiMo-V2.5: 44.2 (#73), Nemotron 3 Ultra: 43.9 (#81)
| Benchmark | MiMo-V2.5 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | 1445 | 1437 |
Writing & Preference Nemotron 3 Ultra leads
MiMo-V2.5: 61.6 (#86), Nemotron 3 Ultra: 66.3 (#36)
| Benchmark | MiMo-V2.5 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | 1428 | 1445 |
| LMArena Creative Writing | 1393 | 1398 |
| LMArena Multi-Turn | 1445 | 1411 |
| EQ-Bench Creative Writing | — | 1692 |
Frequently asked questions
Is MiMo-V2.5 better than Nemotron 3 Ultra?
MiMo-V2.5 and Nemotron 3 Ultra score almost the same on the Noometry Index (43.4 vs 42.5), so choose on price, context window or the category you care about most.
Which is cheaper, MiMo-V2.5 or Nemotron 3 Ultra?
MiMo-V2.5 is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; Nemotron 3 Ultra lists at $0.60 and $2.40.
Is MiMo-V2.5 or Nemotron 3 Ultra better for coding?
MiMo-V2.5 scores higher on coding benchmarks: 43.9 versus 38.1 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.5 does, with 1.05M tokens against 262K.
How many benchmarks do MiMo-V2.5 and Nemotron 3 Ultra share?
19 benchmarks have published results for both models. MiMo-V2.5 has 23 scored results on Noometry and Nemotron 3 Ultra has 30.